About glassdata
glassdata is a local bridge for searching Glassdoor job listings and retrieving full posting details. It is intended for tools and agents that need public job data, and forwards results from HasData without maintaining its own listings.
Key features
- 01Search listings by keyword and location
- 02Filter by date, salary, rating, and remote status
- 03Retrieve full posting details
- 04CLI and stdio MCP server
Use cases
- 01Find roles matching a keyword and location
- 02Narrow listings by salary or posting date
- 03Read a job description and qualifications
MCP support
Exposes two read-only job-data tools to MCP clients and forwards calls to the hosted HasData Glassdoor MCP server. It does not support applications, messaging, or payments.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
2Saved tool list · updated 2d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | The URL of the job vacancy to retrieve details for. |
Details
From the project READMEglassdata
glassdata is a small local bridge to the hosted HasData Glassdoor MCP server, which returns Glassdoor job data as JSON. It can search job listings for a keyword in a place, and it can pull one posting in full from its vacancy URL: the job title, the company and its rating, where the job sits, the salary estimate, when it was posted, the complete description, and the stated qualifications and benefits.
The bridge holds no listings of its own. It answers the tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning whatever comes back untouched. The captured surface is two read-only fetches over public postings: there is no application submission, no employer or candidate contact data, and no messaging or payment tool in it.
Tools
hasdata_glassdoor_listing_getJobListings— search Glassdoor listings. Required:keywordandlocation. Optional:sort(recent/relevant),domain(which national Glassdoor site to target),datePosted(only jobs posted within that many days),radius(search distance in miles),minSalaryandmaxSalary(yearly pay range),minRating(lowest company rating),easyApplyOnlyandremoteOnlyflags, andnextPageTokenfor paging — the token carries the original search's filters with it. Returns jobs with title, company, location, salary estimate, posted date, job URL and jobId, plus per-page tokens.hasdata_glassdoor_job_getJobDetails— fetch one posting in full. Required:url(the vacancy URL). Returns title, company name and rating, location, salary estimate, posted date, full description, and qualifications and benefits.
Configuration
HASDATA_GLASSDOOR_MCP_URL(optional) — override the upstream endpoint. Defaults tohttps://mcp.hasdata.com/mcp?apis=glassdoor. (The override hook is this rebuild's own labelled reconstruction.)HASDATA_API_KEY(optional) — when set, every upstream request carries anx-api-key: <key>header, for the caller's own HasData API key. When it is not set, no key header is sent. (The header name and the env name are pinned by the original's registry record; forwarding the key from this env var is a labelled reconstruction — the original surface was captured keyless.)
Forwarding mechanics
On the first tool call the client opens a streamable
HTTP session upstream: a JSON-RPC initialize request
(protocolVersion 2025-03-26, clientInfo name
glassdata), then a notifications/initialized
notification, then the tools/call request carrying
the caller's arguments unchanged. When the upstream
answers initialize with an Mcp-Session-Id header,
that value rides on every later request of the
session, which is reused for the life of the process.
Replies may arrive as plain JSON or as server-sent
events; both are read.
Successful upstream results pass through verbatim,
including any isError flag the upstream sets.
Failures — a JSON-RPC error, a non-2xx status, an
unreadable response, or a request that cannot be
completed — come back as an isError result whose
text starts with glassdata error: (this rendering
is this rebuild's own labelled reconstruction).
CLI
Each tool is also a subcommand taking one JSON argument string:
npx @reneturcios/glassdata hasdata_glassdoor_listing_getJobListings '{"keyword":"software engineer","location":"San Francisco, California"}'
npx @reneturcios/glassdata hasdata_glassdoor_job_getJobDetails '{"url":"https://www.glassdoor.com/job-listing/example"}'
npx @reneturcios/glassdata --version
Exit codes: 0 on success, 1 on an isError
result, 2 on a usage error.
MCP server
npx -y @reneturcios/glassdata mcp
MCP client config:
{
"mcpServers": {
"glassdata": {
"command": "npx",
"args": ["-y", "@reneturcios/glassdata", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/glassdata
docker run --rm ghcr.io/cloudcorprecords/glassdata --version
The container's default command is mcp, so the first
form is a stdio MCP server; any other arguments reach
the CLI normally.
Development
npm install
npm run build
npm test
npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.